Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 711 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Offline Reinforcement Learning | D4RL Locomotion medium, medium-replay, medium-expert v2 | 34 | Feb 26, 2026 | ||
| Visual Speech Recognition | LRS3 Low-Resource 30h labelled v1 (test) | 34 | Feb 26, 2026 | ||
| Object Detection | MSRS (test) | 34 | Feb 26, 2026 | ||
| Point Cloud Classification | ModelNet40 synthetic (test) | 34 | Feb 26, 2026 | ||
| Video Question Answering | Video-MME Long Duration 1.0 | 34 | Feb 26, 2026 | ||
| OOD Detection | CIFAR-10 vs SVHN (test) | 34 | May 25, 2026 | ||
| Machine Unlearning | TOFU World Fact 1.0 | 34 | May 19, 2026 | ||
| Activity Classification | MOMA Activities (meta-test) | 34 | Feb 26, 2026 | ||
| Few-shot classification | ImageNet mini (test) | 34 | Feb 26, 2026 | ||
| Few-Shot Node Classification | Citeseer 5-shot | 34 | Jun 11, 2026 | ||
| Backdoor Defense | CIFAR-10 Blended v1 (test) | 34 | Feb 26, 2026 | ||
| Open-Ended VideoQA | ANet-QA | 34 | Feb 26, 2026 | ||
| Object Detection | KITTI to Cityscapes K→C | 34 | Feb 26, 2026 | ||
| Image Classification | CIFAR100 | 34 | Feb 26, 2026 | ||
| Image Enhancement | SICE Underexposure v2 | 34 | Feb 26, 2026 | ||
| Boundary Detection | RoFT-chatgpt GPT-3.5-turbo generated (test) | 34 | Feb 26, 2026 | ||
| Segmentation | BDD-100k and LIS entire (test) | 34 | Feb 26, 2026 | ||
| Image-to-Text Retrieval | Urban-1K | 34 | Mar 19, 2026 | ||
| Regression | ACSIncome (test) | 34 | Feb 26, 2026 | ||
| Change Detection | CDD | 34 | Mar 11, 2026 | ||
| Backdoor Attack | ImageNet-1K | 34 | Mar 4, 2026 | ||
| Image Geolocalization | IM2GPS | 34 | Jun 29, 2026 | ||
| Multimodal Cognition | MME Cognition | 34 | Feb 26, 2026 | ||
| Boundary Detection | PASCAL-Context (test) | 34 | Feb 26, 2026 | ||
| 3D Object Classification | Objaverse | 34 | May 22, 2026 |